谐波减速器失效预警方法研究  

Research on Failure Warning of Harmonic Reducer

作　　者：李彬 陶建峰[1] 刘成良[1] 贡亮[1] LI Bin;TAO Jianfeng;LIU Chengliang;GONG Liang(School of Mechanical and Power Engineering Shanghai Jiaotong University,Shanghai 200240,China)

机构地区：[1]上海交通大学机械与动力工程学院,上海200240

出　　处：《机械设计与制造》2025年第3期281-287,292,共8页Machinery Design & Manufacture

基　　金：国家重点研发计划课题(2018YFB1306703);教育部-中国移动联合基金建设项目(CMHQ-JS-201900003)。

摘　　要：谐波减速器是工业机器人的核心部件。在其运行过程中,功率信号是表征谐波减速器运行状态的关键参数,因此实时准确地预测谐波减速器功率,对于其失效预警具有指导性意义。提出了基于CNN和BiLSTM的混合深层神经网络(DCBNN),用于处理谐波减速器状态监测数据从而准确地预测其功率信号。首先,对测得的运行参数进行数据预处理,并划分好数据集。然后,将分割好的数据集输入到DCBNN中,利用CNN和BiLSTM分支提取状态监测数据的空间特征和双向时序依赖。在此基础上,根据预测结果获得功率实际值和预测值残差的绝对值,利用概率论分布拟合方法拟合残差曲线,以获得谐波减速器失效预警的警报阈值。最后,使用谐波减速器实验数据构建的8个不同数据集来验证所提方法的有效性和优越性。在完整数据集上的试验结果表明,DCBNN模型可以有效的对谐波减速器进行失效预警。Harmonic reducer is the core component of industrial robots.During its operation,the power signal is a key parameter that embodies the performance of the harmonic reducer.Therefore,real-time and accurate power prediction of the harmonic reducer has instructive significance for its failure warning and performance prediction.A hybrid deep neural network(DCBNN)based on CNN and BiLSTM was proposed to process the condition monitoring data of the harmonic reducer and improve the prediction accuracy of power signal.First,the operating parameters were preprocessed and the data sets were divided.Then,the preprocessed data were input into DCBNN,and the spatial characteristics and bidirectional timing dependencies of the condition monitoring data are captured by CNN and BiLSTM.On this basis,the absolute value of the residual of the actual power and the predicted value is obtained according to the prediction result,and the residual curve is fitted by the distribution fitting method to obtain the alarm threshold of the harmonic reducer failure warning.Finally,8 different data sets constructed using the experimental data of the harmonic reducer are used to verify the effectiveness and superiority of the proposed method.The test results on the complete data set show that the DCBNN model can complete effectively failure warning of the harmonic reducer.

关 键 词：失效预警 谐波减速器 功率预测 卷积神经网络 双向长短期记忆神经网络 深度学习 

分 类 号：TH16[机械工程—机械制造及自动化] TH17[自动化与计算机技术—控制理论与控制工程] TP181[自动化与计算机技术—控制科学与工程]